|
0
|
1 <tool id="bowtieForSmallRNA" name="sRbowtie" version="1.1.0">
|
|
|
2 <description>for FASTA small reads</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="0.12.7">bowtie</requirement>
|
|
|
5 <requirement type="package" version="0.1.18">samtools</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command interpreter="python"> sRbowtie.py --input $input
|
|
|
8 --input-format $input.extension
|
|
|
9 --method $method
|
|
|
10 --v-mismatches $v_mismatches
|
|
|
11 --output-format $output_format
|
|
|
12 --output $output
|
|
|
13 --index-from $refGenomeSource.genomeSource
|
|
|
14 ## the very source of the index (indexed or fasta file)
|
|
|
15 --index-source
|
|
|
16 #if $refGenomeSource.genomeSource == "history":
|
|
|
17 $refGenomeSource.ownFile
|
|
|
18 #else:
|
|
|
19 $refGenomeSource.index.fields.path
|
|
|
20 #end if
|
|
|
21 --aligned $aligned
|
|
|
22 --unaligned $unaligned
|
|
|
23 --num-threads \${GALAXY_SLOTS:-4} ## number of processors to be handled by bowtie
|
|
|
24 </command>
|
|
|
25 <inputs>
|
|
|
26 <param format="fasta, fastq" help="Only with clipped, raw fasta files" label="Input fasta file: reads clipped from their adapter" name="input" type="data" />
|
|
|
27 <param help="bowtie parameters adjusted to the type of matching. RNA option match to only one strand" label="What kind of matching do you want to do?" name="method" type="select">
|
|
|
28 <option value="RNA">Match on sense strand RNA reference index, multiple mappers randomly matched at a single position</option>
|
|
|
29 <option value="unique">Match unique mappers on DNA reference index</option>
|
|
|
30 <option selected="true" value="multiple">Match on DNA, multiple mappers randomly matched at a single position</option>
|
|
|
31 <option value="k_option">Match on DNA as fast as possible, without taking care of mapping issues (for raw annotation of reads)</option>
|
|
|
32 <option value="n_option">Match on DNA - RNAseq mode (-n bowtie option)</option>
|
|
|
33 <option value="a_option">Match and report all valid alignments</option>
|
|
|
34 </param>
|
|
|
35 <param help="specify the -v bowtie option" label="Number of mismatches allowed" name="v_mismatches" type="select">
|
|
|
36 <option value="0">0</option>
|
|
|
37 <option selected="true" value="1">1</option>
|
|
|
38 <option value="2">2</option>
|
|
|
39 <option value="3">3</option>
|
|
|
40 </param>
|
|
|
41 <conditional name="refGenomeSource">
|
|
|
42 <param help="Built-ins were indexed using default options" label="Will you select a reference genome from your history or use a built-in index?" name="genomeSource" type="select">
|
|
|
43 <option value="indexed">Use a built-in index</option>
|
|
|
44 <option value="history">Use one from the history</option>
|
|
|
45 </param>
|
|
|
46 <when value="indexed">
|
|
|
47 <param help="if your genome of interest is not listed - contact instance administrator" label="Select a DNA reference index" name="index" type="select">
|
|
|
48 <options from_data_table="bowtie_indexes">
|
|
|
49
|
|
|
50 </options>
|
|
|
51 </param>
|
|
|
52 </when>
|
|
|
53 <when value="history">
|
|
|
54 <param format="fasta" label="Select a fasta file, to serve as index reference" name="ownFile" type="data" />
|
|
|
55 </when>
|
|
|
56 </conditional>
|
|
|
57 <param help="Note that the BAM will be viewable in trackster only if you choose a full genome referenced for Trackster usage. see the doc below" label="Select output format" name="output_format" type="select">
|
|
|
58 <option select="true" value="tabular">tabular</option>
|
|
|
59 <option value="sam">sam</option>
|
|
|
60 <option value="bam">bam</option>
|
|
|
61 </param>
|
|
|
62 <param help="to get aligned and unaligned reads in fasta format" label="additional fasta output" name="additional_fasta" type="select">
|
|
|
63 <option select="true" value="No">No</option>
|
|
|
64 <option value="al">aligned</option>
|
|
|
65 <option value="unal">unaligned</option>
|
|
|
66 <option value="al_and_unal">both aligned and unaligned</option>
|
|
|
67 </param>
|
|
|
68 </inputs>
|
|
|
69 <outputs>
|
|
|
70 <data format="tabular" label="Bowtie Output" name="output">
|
|
|
71 <change_format>
|
|
|
72 <when format="sam" input="output_format" value="sam" />
|
|
|
73 <when format="bam" input="output_format" value="bam" />
|
|
|
74 </change_format>
|
|
|
75 <actions>
|
|
|
76 <conditional name="refGenomeSource.genomeSource">
|
|
|
77 <when value="indexed">
|
|
|
78 <action name="dbkey" type="metadata">
|
|
|
79 <option column="1" name="bowtie_indexes" offset="0" type="from_data_table">
|
|
|
80 <filter column="0" compare="startswith" keep="False" type="param_value" value="#" />
|
|
|
81 <filter column="0" ref="refGenomeSource.index" type="param_value" />
|
|
|
82 </option>
|
|
|
83 </action>
|
|
|
84 </when>
|
|
|
85 <when value="history">
|
|
|
86 <action name="dbkey" type="metadata">
|
|
|
87 <option name="refGenomeSource.ownFile" param_attribute="dbkey" type="from_param" />
|
|
|
88 </action>
|
|
|
89 </when>
|
|
|
90 </conditional>
|
|
|
91 </actions>
|
|
|
92 </data>
|
|
|
93 <data format="fasta" label="Matched reads" name="aligned">
|
|
|
94 <filter>additional_fasta == "al" or additional_fasta == "al_and_unal"</filter>
|
|
|
95 </data>
|
|
|
96 <data format="fasta" label="Unmatched reads" name="unaligned">
|
|
|
97 <filter>additional_fasta == "unal" or additional_fasta == "al_and_unal"</filter>
|
|
|
98 </data>
|
|
|
99 </outputs>
|
|
|
100 <tests>
|
|
|
101 <test>
|
|
|
102 <param name="genomeSource" value="history" />
|
|
|
103 <param ftype="fasta" name="ownFile" value="297_reference.fa" />
|
|
|
104 <param name="method" value="unique" />
|
|
|
105 <param ftype="fasta" name="input" value="input.fa" />
|
|
|
106 <param name="v_mismatches" value="1" />
|
|
|
107 <param name="output_format" value="bam" />
|
|
|
108 <output file="output.bam" ftype="bam" lines_diff="4" name="output" />
|
|
|
109 </test>
|
|
|
110 <test>
|
|
|
111 <param name="genomeSource" value="history" />
|
|
|
112 <param ftype="fasta" name="ownFile" value="297_reference.fa" />
|
|
|
113 <param name="method" value="unique" />
|
|
|
114 <param ftype="fastq" name="input" value="input.fastq" />
|
|
|
115 <param name="v_mismatches" value="1" />
|
|
|
116 <param name="output_format" value="bam" />
|
|
|
117 <output file="output2.bam" ftype="bam" lines_diff="4" name="output" />
|
|
|
118 </test>
|
|
|
119 </tests>
|
|
|
120 <help>
|
|
|
121
|
|
|
122 **What it does**
|
|
|
123
|
|
|
124 Bowtie_ is a short read aligner designed to be ultrafast and memory-efficient. It is developed by Ben Langmead and Cole Trapnell. Please cite: Langmead B, Trapnell C, Pop M, Salzberg SL. Ultrafast and memory-efficient alignment of short DNA sequences to the human genome. Genome Biology 10:R25.
|
|
|
125
|
|
|
126 .. _Bowtie: http://bowtie-bio.sourceforge.net/index.shtml
|
|
|
127
|
|
|
128 A generic "Map with Bowtie for Illumina" Galaxy tool is available in the main Galaxy distribution.
|
|
|
129
|
|
|
130 However, this Bowtie wrapper tool only takes FASTQ files as inputs.
|
|
|
131
|
|
|
132 The sRbowtie wrapper specifically works with short reads FASTA inputs (-v bowtie mode)
|
|
|
133
|
|
|
134 ------
|
|
|
135
|
|
|
136 **OPTIONS**
|
|
|
137
|
|
|
138 .. class:: infomark
|
|
|
139
|
|
|
140 This script uses Bowtie to match reads on a reference index.
|
|
|
141
|
|
|
142 Depending on the type of matching, different bowtie options are used:
|
|
|
143
|
|
|
144 **Match on sense strand RNA reference index, multiple mappers randomly matched at a single position**
|
|
|
145
|
|
|
146 Match on RNA reference, SENSE strand, randomly attributing multiple mapper to target with least mismatches, the polarity column is suppressed in the bowtie tabular report:
|
|
|
147
|
|
|
148 *-v [0,1,2,3] -M 1 --best --strata -p 12 --norc --suppress 2,6,7,8*
|
|
|
149
|
|
|
150 **Match unique mappers on DNA reference index**
|
|
|
151
|
|
|
152 Match ONLY unique mappers on DNA reference index
|
|
|
153
|
|
|
154 *-v [0,1,2,3] -m 1 -p 12 --suppress 6,7,8*
|
|
|
155
|
|
|
156 Note that using this option with -v values other than 0 is questionnable...
|
|
|
157
|
|
|
158 **Match on DNA, multiple mappers randomly matched at a single position**
|
|
|
159
|
|
|
160 Match multiple mappers, randomly attributing multiple mapper to target with least mismatches, number of mismatch allowed specified by -v option:
|
|
|
161
|
|
|
162 *-v [0,1,2,3] -M 1 --best --strata -p 12 --suppress 6,7,8*
|
|
|
163
|
|
|
164 **Match on DNA as fast as possible, without taking care of mapping issues (for raw annotation of reads)**
|
|
|
165
|
|
|
166 Match with highest speed, not guaranteeing best hit for speed gain:
|
|
|
167
|
|
|
168 *-v [0,1,2,3] -k 1 --best -p 12 --suppress 6,7,8*
|
|
|
169
|
|
|
170
|
|
|
171 -----
|
|
|
172
|
|
|
173 **Input formats**
|
|
|
174
|
|
|
175 .. class:: warningmark
|
|
|
176
|
|
|
177 *The only accepted format for the script is a raw fasta list of reads, clipped from their adapter*
|
|
|
178
|
|
|
179 -----
|
|
|
180
|
|
|
181 **OUTPUTS**
|
|
|
182
|
|
|
183 If you choose tabular as the output format, you will obtain the matched reads in standard bowtie output format, having the following columns::
|
|
|
184
|
|
|
185 Column Description
|
|
|
186 -------- --------------------------------------------------------
|
|
|
187 1 FastaID fasta identifier
|
|
|
188 2 polarity + or - depending whether the match was reported on the forward or reverse strand
|
|
|
189 3 target name of the matched target
|
|
|
190 4 Offset O-based coordinate of the miR on the miRBase pre-miR sequence
|
|
|
191 5 Seq sequence of the matched Read
|
|
|
192
|
|
|
193 If you choose SAM, you will get the output in unordered SAM format.
|
|
|
194
|
|
|
195 .. class:: warningmark
|
|
|
196
|
|
|
197 if you choose BAM, the output will be in sorted BAM format.
|
|
|
198 To be viewable in Trackster, several condition must be fulfilled:
|
|
|
199
|
|
|
200 .. class:: infomark
|
|
|
201
|
|
|
202 Reads must have been matched to a genome whose chromosome names are compatible with Trackster genome indexes
|
|
|
203
|
|
|
204 .. class:: infomark
|
|
|
205
|
|
|
206 the database/Build (dbkey) which is indicated for the dataset (Pencil - Database/Build field) must match a Trackster genome index.
|
|
|
207
|
|
|
208 Please contact the Galaxy instance administrator if your genome is not referenced
|
|
|
209
|
|
|
210 **Matched and unmatched fasta reads can be retrieved, for further analyses**
|
|
|
211
|
|
|
212 </help>
|
|
|
213 <citations>
|
|
|
214 <citation type="doi">10.1186/gb-2009-10-3-r25</citation>
|
|
|
215 </citations>
|
|
|
216 </tool>
|
